MDFM: Multi-Decision Fusing Model for Few-Shot Learning

Abstract

In recent years, researchers pay growing attention to the few-shot learning (FSL) task to address the data-scarce problem. A standard FSL framework is composed of two components: i) Pre-train. Employ the base data to generate a CNN-based feature extraction model (FEM). ii) Meta-test. Apply the trained FEM to the novel data (category is different from base data) to acquire the feature embeddings and recognize them. Although researchers have made remarkable breakthroughs in FSL, there still exists a fundamental problem. Since the trained FEM with base data usually cannot adapt to the novel class flawlessly, the novel data's feature may lead to the distribution shift problem. To address this challenge, we hypothesize that even if most of the decisions based on different FEMs are viewed as weak decisions, which are not available for all classes, they still perform decently in some specific categories. Inspired by this assumption, we propose a novel method Multi-Decision Fusing Model (MDFM), which comprehensively considers the decisions based on multiple FEMs to enhance the efficacy and robustness of the model. MDFM is a simple, flexible, non-parametric method that can directly apply to the existing FEMs. Besides, we extend the proposed MDFM to two FSL settings (i.e., supervised and semi-supervised settings). We evaluate the proposed method on five benchmark datasets and achieve significant improvements of 3.4%-7.3% compared with state-of-the-arts.

arXiv commentAccepted by IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). arXiv admin note: text overlap with arXiv:2109.07785

References in corpus (16)

• Scikit-learn: Machine Learning in Python
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Cost-Effective Active Learning for Deep Image Classification
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• On First-Order Meta-Learning Algorithms
• Manifold Mixup: Better Representations by Interpolating Hidden States
• Free Lunch for Few-shot Learning: Distribution Calibration
• Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
• TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
• Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning
• BOIL: Towards Representation Change for Few-shot Learning
• Transductive Information Maximization For Few-Shot Learning
• Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning
• MHFC: Multi-Head Feature Collaboration for Few-Shot Learning